audrey 1.1.0 → 1.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +8 -0
- package/README.md +14 -7
- package/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +4 -4
- package/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
- package/benchmarks/output/external/guardbench-external-evidence.json +1 -1
- package/benchmarks/output/guardbench-conformance-card.json +9 -9
- package/benchmarks/output/guardbench-raw.json +104 -104
- package/benchmarks/output/guardbench-summary.json +163 -163
- package/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
- package/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
- package/benchmarks/output/submission-bundle/guardbench-conformance-card.json +9 -9
- package/benchmarks/output/submission-bundle/guardbench-raw.json +104 -104
- package/benchmarks/output/submission-bundle/guardbench-summary.json +163 -163
- package/benchmarks/output/submission-bundle/submission-manifest.json +10 -10
- package/benchmarks/output/submission-bundle/validation-report.json +1 -1
- package/benchmarks/output/summary.json +67 -67
- package/dist/mcp-server/config.d.ts +1 -1
- package/dist/mcp-server/config.js +1 -1
- package/dist/mcp-server/index.d.ts.map +1 -1
- package/dist/mcp-server/index.js +20 -19
- package/dist/mcp-server/index.js.map +1 -1
- package/dist/src/preflight.d.ts.map +1 -1
- package/dist/src/preflight.js +3 -3
- package/dist/src/preflight.js.map +1 -1
- package/docs/paper/07-evaluation.md +4 -4
- package/docs/paper/audrey-paper-v1.md +4 -4
- package/docs/paper/evidence-ledger.md +1 -1
- package/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
- package/docs/paper/output/arxiv/main.tex +4 -4
- package/docs/paper/output/arxiv-compile-report.json +3 -3
- package/docs/paper/output/submission-bundle/README.md +14 -7
- package/docs/paper/output/submission-bundle/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +4 -4
- package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
- package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-evidence.json +1 -1
- package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-conformance-card.json +9 -9
- package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-raw.json +104 -104
- package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-summary.json +163 -163
- package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
- package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
- package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/submission-manifest.json +10 -10
- package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/validation-report.json +1 -1
- package/docs/paper/output/submission-bundle/benchmarks/output/summary.json +56 -56
- package/docs/paper/output/submission-bundle/docs/paper/07-evaluation.md +4 -4
- package/docs/paper/output/submission-bundle/docs/paper/audrey-paper-v1.md +4 -4
- package/docs/paper/output/submission-bundle/docs/paper/evidence-ledger.md +1 -1
- package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
- package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/main.tex +4 -4
- package/docs/paper/output/submission-bundle/docs/paper/output/arxiv-compile-report.json +3 -3
- package/docs/paper/output/submission-bundle/package.json +7 -1
- package/docs/paper/output/submission-bundle/paper-submission-manifest.json +31 -31
- package/package.json +7 -1
- package/scripts/audit-release-completion.mjs +1 -1
- package/scripts/finalize-release.mjs +1 -1
- package/scripts/prepare-release-cut.mjs +1 -1
- package/scripts/publish-release-bundle.mjs +1 -1
- package/scripts/publish-release-github-api.mjs +1 -1
- package/scripts/verify-release-readiness.mjs +1 -1
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"schemaVersion": "1.0.0",
|
|
3
3
|
"suite": "GuardBench submission bundle",
|
|
4
|
-
"generatedAt": "2026-07-10T15:
|
|
4
|
+
"generatedAt": "2026-07-10T15:18:56.715Z",
|
|
5
5
|
"sourceDir": "benchmarks/output",
|
|
6
6
|
"subject": {
|
|
7
7
|
"name": "Audrey Guard",
|
|
@@ -16,9 +16,9 @@
|
|
|
16
16
|
"evidenceRecall": 1,
|
|
17
17
|
"redactionLeaks": 0,
|
|
18
18
|
"latency": {
|
|
19
|
-
"p50Ms": 3.
|
|
20
|
-
"p95Ms":
|
|
21
|
-
"maxMs":
|
|
19
|
+
"p50Ms": 3.075,
|
|
20
|
+
"p95Ms": 17.056,
|
|
21
|
+
"maxMs": 17.056
|
|
22
22
|
}
|
|
23
23
|
},
|
|
24
24
|
"conformance": {
|
|
@@ -45,7 +45,7 @@
|
|
|
45
45
|
{
|
|
46
46
|
"path": "guardbench-conformance-card.json",
|
|
47
47
|
"bytes": 1735,
|
|
48
|
-
"sha256": "
|
|
48
|
+
"sha256": "77ff197cb2ac40038f2dd823a0cb5e84fcc2e18e03f15c802bcec4511cb9520f"
|
|
49
49
|
},
|
|
50
50
|
{
|
|
51
51
|
"path": "guardbench-manifest.json",
|
|
@@ -54,13 +54,13 @@
|
|
|
54
54
|
},
|
|
55
55
|
{
|
|
56
56
|
"path": "guardbench-raw.json",
|
|
57
|
-
"bytes":
|
|
58
|
-
"sha256": "
|
|
57
|
+
"bytes": 43436,
|
|
58
|
+
"sha256": "46026c7bd5add25bf7aed89357b958b012bcd46549dc7dd6d31362cef0a0e00f"
|
|
59
59
|
},
|
|
60
60
|
{
|
|
61
61
|
"path": "guardbench-summary.json",
|
|
62
|
-
"bytes":
|
|
63
|
-
"sha256": "
|
|
62
|
+
"bytes": 69311,
|
|
63
|
+
"sha256": "420c3d8188cdc636459ad034d6e5ee3836bdf9e649aa3febe5ce087d681a98bb"
|
|
64
64
|
},
|
|
65
65
|
{
|
|
66
66
|
"path": "schemas/guardbench-adapter-registry.schema.json",
|
|
@@ -125,7 +125,7 @@
|
|
|
125
125
|
{
|
|
126
126
|
"path": "validation-report.json",
|
|
127
127
|
"bytes": 739,
|
|
128
|
-
"sha256": "
|
|
128
|
+
"sha256": "0b51d31416c5bc4789c130ab22523a38fe5ae58f089475ebccc71c697e2295ea"
|
|
129
129
|
}
|
|
130
130
|
]
|
|
131
131
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"generatedAt": "2026-07-10T15:
|
|
2
|
+
"generatedAt": "2026-07-10T15:21:19.649Z",
|
|
3
3
|
"command": "node benchmarks/run.js --provider mock --dimensions 64",
|
|
4
4
|
"config": {
|
|
5
5
|
"provider": "mock",
|
|
@@ -23,25 +23,25 @@
|
|
|
23
23
|
"system": "Audrey",
|
|
24
24
|
"scorePercent": 100,
|
|
25
25
|
"passRate": 100,
|
|
26
|
-
"avgDurationMs":
|
|
26
|
+
"avgDurationMs": 200.16666666666666
|
|
27
27
|
},
|
|
28
28
|
{
|
|
29
29
|
"system": "Vector Only",
|
|
30
30
|
"scorePercent": 41.66666666666667,
|
|
31
31
|
"passRate": 25,
|
|
32
|
-
"avgDurationMs": 0.
|
|
32
|
+
"avgDurationMs": 0.25
|
|
33
33
|
},
|
|
34
34
|
{
|
|
35
35
|
"system": "Keyword + Recency",
|
|
36
36
|
"scorePercent": 41.66666666666667,
|
|
37
37
|
"passRate": 25,
|
|
38
|
-
"avgDurationMs": 0.
|
|
38
|
+
"avgDurationMs": 0.75
|
|
39
39
|
},
|
|
40
40
|
{
|
|
41
41
|
"system": "Recent Window",
|
|
42
42
|
"scorePercent": 37.5,
|
|
43
43
|
"passRate": 25,
|
|
44
|
-
"avgDurationMs": 0
|
|
44
|
+
"avgDurationMs": 0.08333333333333333
|
|
45
45
|
}
|
|
46
46
|
],
|
|
47
47
|
"overall_scope": "comparable_suites",
|
|
@@ -170,13 +170,13 @@
|
|
|
170
170
|
"system": "Audrey",
|
|
171
171
|
"scorePercent": 100,
|
|
172
172
|
"passRate": 100,
|
|
173
|
-
"avgDurationMs":
|
|
173
|
+
"avgDurationMs": 262.625
|
|
174
174
|
},
|
|
175
175
|
{
|
|
176
176
|
"system": "Vector Only",
|
|
177
177
|
"scorePercent": 56.25,
|
|
178
178
|
"passRate": 37.5,
|
|
179
|
-
"avgDurationMs": 0.
|
|
179
|
+
"avgDurationMs": 0.125
|
|
180
180
|
},
|
|
181
181
|
{
|
|
182
182
|
"system": "Keyword + Recency",
|
|
@@ -188,7 +188,7 @@
|
|
|
188
188
|
"system": "Recent Window",
|
|
189
189
|
"scorePercent": 50,
|
|
190
190
|
"passRate": 37.5,
|
|
191
|
-
"avgDurationMs": 0
|
|
191
|
+
"avgDurationMs": 0.125
|
|
192
192
|
}
|
|
193
193
|
],
|
|
194
194
|
"byFamily": [
|
|
@@ -277,7 +277,7 @@
|
|
|
277
277
|
"results": [
|
|
278
278
|
{
|
|
279
279
|
"system": "Audrey",
|
|
280
|
-
"durationMs":
|
|
280
|
+
"durationMs": 89,
|
|
281
281
|
"passed": true,
|
|
282
282
|
"score": 1,
|
|
283
283
|
"summary": "retrieved expected evidence",
|
|
@@ -289,7 +289,7 @@
|
|
|
289
289
|
},
|
|
290
290
|
{
|
|
291
291
|
"system": "Vector Only",
|
|
292
|
-
"durationMs":
|
|
292
|
+
"durationMs": 0,
|
|
293
293
|
"passed": true,
|
|
294
294
|
"score": 1,
|
|
295
295
|
"summary": "retrieved expected evidence",
|
|
@@ -301,7 +301,7 @@
|
|
|
301
301
|
},
|
|
302
302
|
{
|
|
303
303
|
"system": "Keyword + Recency",
|
|
304
|
-
"durationMs":
|
|
304
|
+
"durationMs": 6,
|
|
305
305
|
"passed": true,
|
|
306
306
|
"score": 1,
|
|
307
307
|
"summary": "retrieved expected evidence",
|
|
@@ -313,7 +313,7 @@
|
|
|
313
313
|
},
|
|
314
314
|
{
|
|
315
315
|
"system": "Recent Window",
|
|
316
|
-
"durationMs":
|
|
316
|
+
"durationMs": 1,
|
|
317
317
|
"passed": true,
|
|
318
318
|
"score": 1,
|
|
319
319
|
"summary": "retrieved expected evidence",
|
|
@@ -336,7 +336,7 @@
|
|
|
336
336
|
"results": [
|
|
337
337
|
{
|
|
338
338
|
"system": "Audrey",
|
|
339
|
-
"durationMs":
|
|
339
|
+
"durationMs": 555,
|
|
340
340
|
"passed": true,
|
|
341
341
|
"score": 1,
|
|
342
342
|
"summary": "retrieved expected evidence",
|
|
@@ -359,7 +359,7 @@
|
|
|
359
359
|
},
|
|
360
360
|
{
|
|
361
361
|
"system": "Keyword + Recency",
|
|
362
|
-
"durationMs":
|
|
362
|
+
"durationMs": 0,
|
|
363
363
|
"passed": false,
|
|
364
364
|
"score": 0.5,
|
|
365
365
|
"summary": "retrieved expected evidence, but conflicting evidence still appeared later",
|
|
@@ -394,7 +394,7 @@
|
|
|
394
394
|
"results": [
|
|
395
395
|
{
|
|
396
396
|
"system": "Audrey",
|
|
397
|
-
"durationMs":
|
|
397
|
+
"durationMs": 418,
|
|
398
398
|
"passed": true,
|
|
399
399
|
"score": 1,
|
|
400
400
|
"summary": "retrieved expected evidence",
|
|
@@ -457,7 +457,7 @@
|
|
|
457
457
|
"results": [
|
|
458
458
|
{
|
|
459
459
|
"system": "Audrey",
|
|
460
|
-
"durationMs":
|
|
460
|
+
"durationMs": 358,
|
|
461
461
|
"passed": true,
|
|
462
462
|
"score": 1,
|
|
463
463
|
"summary": "retrieved expected evidence",
|
|
@@ -518,7 +518,7 @@
|
|
|
518
518
|
"results": [
|
|
519
519
|
{
|
|
520
520
|
"system": "Audrey",
|
|
521
|
-
"durationMs":
|
|
521
|
+
"durationMs": 289,
|
|
522
522
|
"passed": true,
|
|
523
523
|
"score": 1,
|
|
524
524
|
"summary": "correct abstention",
|
|
@@ -574,7 +574,7 @@
|
|
|
574
574
|
"results": [
|
|
575
575
|
{
|
|
576
576
|
"system": "Audrey",
|
|
577
|
-
"durationMs":
|
|
577
|
+
"durationMs": 149,
|
|
578
578
|
"passed": true,
|
|
579
579
|
"score": 1,
|
|
580
580
|
"summary": "retrieved expected evidence",
|
|
@@ -585,7 +585,7 @@
|
|
|
585
585
|
},
|
|
586
586
|
{
|
|
587
587
|
"system": "Vector Only",
|
|
588
|
-
"durationMs":
|
|
588
|
+
"durationMs": 0,
|
|
589
589
|
"passed": false,
|
|
590
590
|
"score": 0.5,
|
|
591
591
|
"summary": "retrieved expected evidence, but conflicting evidence still appeared later",
|
|
@@ -597,7 +597,7 @@
|
|
|
597
597
|
},
|
|
598
598
|
{
|
|
599
599
|
"system": "Keyword + Recency",
|
|
600
|
-
"durationMs":
|
|
600
|
+
"durationMs": 1,
|
|
601
601
|
"passed": false,
|
|
602
602
|
"score": 0,
|
|
603
603
|
"summary": "blocked content outranked the correct answer",
|
|
@@ -632,7 +632,7 @@
|
|
|
632
632
|
"results": [
|
|
633
633
|
{
|
|
634
634
|
"system": "Audrey",
|
|
635
|
-
"durationMs":
|
|
635
|
+
"durationMs": 32,
|
|
636
636
|
"passed": true,
|
|
637
637
|
"score": 1,
|
|
638
638
|
"summary": "retrieved expected evidence",
|
|
@@ -656,7 +656,7 @@
|
|
|
656
656
|
},
|
|
657
657
|
{
|
|
658
658
|
"system": "Keyword + Recency",
|
|
659
|
-
"durationMs":
|
|
659
|
+
"durationMs": 1,
|
|
660
660
|
"passed": false,
|
|
661
661
|
"score": 0,
|
|
662
662
|
"summary": "missed target evidence",
|
|
@@ -693,7 +693,7 @@
|
|
|
693
693
|
"results": [
|
|
694
694
|
{
|
|
695
695
|
"system": "Audrey",
|
|
696
|
-
"durationMs":
|
|
696
|
+
"durationMs": 211,
|
|
697
697
|
"passed": true,
|
|
698
698
|
"score": 1,
|
|
699
699
|
"summary": "correct abstention",
|
|
@@ -750,13 +750,13 @@
|
|
|
750
750
|
"system": "Audrey",
|
|
751
751
|
"scorePercent": 100,
|
|
752
752
|
"passRate": 100,
|
|
753
|
-
"avgDurationMs":
|
|
753
|
+
"avgDurationMs": 75.25
|
|
754
754
|
},
|
|
755
755
|
{
|
|
756
756
|
"system": "Keyword + Recency",
|
|
757
757
|
"scorePercent": 25,
|
|
758
758
|
"passRate": 0,
|
|
759
|
-
"avgDurationMs": 0
|
|
759
|
+
"avgDurationMs": 0.25
|
|
760
760
|
},
|
|
761
761
|
{
|
|
762
762
|
"system": "Vector Only",
|
|
@@ -821,7 +821,7 @@
|
|
|
821
821
|
"results": [
|
|
822
822
|
{
|
|
823
823
|
"system": "Audrey",
|
|
824
|
-
"durationMs":
|
|
824
|
+
"durationMs": 19,
|
|
825
825
|
"passed": true,
|
|
826
826
|
"score": 1,
|
|
827
827
|
"summary": "retrieved expected evidence",
|
|
@@ -844,7 +844,7 @@
|
|
|
844
844
|
},
|
|
845
845
|
{
|
|
846
846
|
"system": "Keyword + Recency",
|
|
847
|
-
"durationMs":
|
|
847
|
+
"durationMs": 1,
|
|
848
848
|
"passed": false,
|
|
849
849
|
"score": 0.5,
|
|
850
850
|
"summary": "retrieved expected evidence, but conflicting evidence still appeared later",
|
|
@@ -879,7 +879,7 @@
|
|
|
879
879
|
"results": [
|
|
880
880
|
{
|
|
881
881
|
"system": "Audrey",
|
|
882
|
-
"durationMs":
|
|
882
|
+
"durationMs": 148,
|
|
883
883
|
"passed": true,
|
|
884
884
|
"score": 1,
|
|
885
885
|
"summary": "correct abstention",
|
|
@@ -932,7 +932,7 @@
|
|
|
932
932
|
"results": [
|
|
933
933
|
{
|
|
934
934
|
"system": "Audrey",
|
|
935
|
-
"durationMs":
|
|
935
|
+
"durationMs": 110,
|
|
936
936
|
"passed": true,
|
|
937
937
|
"score": 1,
|
|
938
938
|
"summary": "retrieved expected evidence",
|
|
@@ -943,7 +943,7 @@
|
|
|
943
943
|
},
|
|
944
944
|
{
|
|
945
945
|
"system": "Vector Only",
|
|
946
|
-
"durationMs":
|
|
946
|
+
"durationMs": 1,
|
|
947
947
|
"passed": false,
|
|
948
948
|
"score": 0,
|
|
949
949
|
"summary": "missed target evidence",
|
|
@@ -993,7 +993,7 @@
|
|
|
993
993
|
"results": [
|
|
994
994
|
{
|
|
995
995
|
"system": "Audrey",
|
|
996
|
-
"durationMs":
|
|
996
|
+
"durationMs": 24,
|
|
997
997
|
"passed": true,
|
|
998
998
|
"score": 1,
|
|
999
999
|
"summary": "retrieved expected evidence",
|
|
@@ -1004,7 +1004,7 @@
|
|
|
1004
1004
|
},
|
|
1005
1005
|
{
|
|
1006
1006
|
"system": "Vector Only",
|
|
1007
|
-
"durationMs":
|
|
1007
|
+
"durationMs": 0,
|
|
1008
1008
|
"passed": false,
|
|
1009
1009
|
"score": 0,
|
|
1010
1010
|
"summary": "missed target evidence",
|
|
@@ -1055,7 +1055,7 @@
|
|
|
1055
1055
|
"system": "Audrey",
|
|
1056
1056
|
"scorePercent": 100,
|
|
1057
1057
|
"passRate": 100,
|
|
1058
|
-
"avgDurationMs":
|
|
1058
|
+
"avgDurationMs": 102.75
|
|
1059
1059
|
},
|
|
1060
1060
|
{
|
|
1061
1061
|
"system": "Vector Only",
|
|
@@ -1118,7 +1118,7 @@
|
|
|
1118
1118
|
"results": [
|
|
1119
1119
|
{
|
|
1120
1120
|
"system": "Audrey",
|
|
1121
|
-
"durationMs":
|
|
1121
|
+
"durationMs": 361,
|
|
1122
1122
|
"passed": true,
|
|
1123
1123
|
"score": 1,
|
|
1124
1124
|
"summary": "matched all required signals",
|
|
@@ -1176,7 +1176,7 @@
|
|
|
1176
1176
|
"results": [
|
|
1177
1177
|
{
|
|
1178
1178
|
"system": "Audrey",
|
|
1179
|
-
"durationMs":
|
|
1179
|
+
"durationMs": 19,
|
|
1180
1180
|
"passed": true,
|
|
1181
1181
|
"score": 1,
|
|
1182
1182
|
"summary": "matched all required signals",
|
|
@@ -1234,12 +1234,12 @@
|
|
|
1234
1234
|
"results": [
|
|
1235
1235
|
{
|
|
1236
1236
|
"system": "Audrey",
|
|
1237
|
-
"durationMs":
|
|
1237
|
+
"durationMs": 18,
|
|
1238
1238
|
"passed": true,
|
|
1239
1239
|
"score": 1,
|
|
1240
1240
|
"summary": "matched all required signals",
|
|
1241
1241
|
"topResults": [
|
|
1242
|
-
"guard_hardened:replay_rejected error:guard receipt already has an outcome:
|
|
1242
|
+
"guard_hardened:replay_rejected error:guard receipt already has an outcome: 01KX69WW0CVDB2V94KQA9KSW24",
|
|
1243
1243
|
"decision:caution verdict:caution risk:0.55 Caution: 1 memory signal, 1 medium severity found before acting.",
|
|
1244
1244
|
"warning:recent_failure severity:medium npm test failed 1x recently: Vitest failed with spawn EPERM Before re-running npm test, check what changed since the last failure."
|
|
1245
1245
|
],
|
|
@@ -1292,12 +1292,12 @@
|
|
|
1292
1292
|
"results": [
|
|
1293
1293
|
{
|
|
1294
1294
|
"system": "Audrey",
|
|
1295
|
-
"durationMs":
|
|
1295
|
+
"durationMs": 13,
|
|
1296
1296
|
"passed": true,
|
|
1297
1297
|
"score": 1,
|
|
1298
1298
|
"summary": "matched all required signals",
|
|
1299
1299
|
"topResults": [
|
|
1300
|
-
"guard_hardened:non_guard_receipt_rejected error:not a guard receipt:
|
|
1300
|
+
"guard_hardened:non_guard_receipt_rejected error:not a guard receipt: 01KX69WW0TRRANA9TAAT45W6FE",
|
|
1301
1301
|
"decision:go verdict:clear risk:0 No relevant memory risks, prior failures, or must-follow procedures were found."
|
|
1302
1302
|
],
|
|
1303
1303
|
"retrievalSummary": "guard_hardened:non_guard_receipt_rejected error:not a guard receipt: 01K | decision:go verdict:clear risk:0 No relevant memory risks, prior failure"
|
|
@@ -1352,7 +1352,7 @@
|
|
|
1352
1352
|
"results": [
|
|
1353
1353
|
{
|
|
1354
1354
|
"system": "Audrey",
|
|
1355
|
-
"durationMs":
|
|
1355
|
+
"durationMs": 89,
|
|
1356
1356
|
"passed": true,
|
|
1357
1357
|
"score": 1,
|
|
1358
1358
|
"summary": "retrieved expected evidence",
|
|
@@ -1364,7 +1364,7 @@
|
|
|
1364
1364
|
},
|
|
1365
1365
|
{
|
|
1366
1366
|
"system": "Vector Only",
|
|
1367
|
-
"durationMs":
|
|
1367
|
+
"durationMs": 0,
|
|
1368
1368
|
"passed": true,
|
|
1369
1369
|
"score": 1,
|
|
1370
1370
|
"summary": "retrieved expected evidence",
|
|
@@ -1376,7 +1376,7 @@
|
|
|
1376
1376
|
},
|
|
1377
1377
|
{
|
|
1378
1378
|
"system": "Keyword + Recency",
|
|
1379
|
-
"durationMs":
|
|
1379
|
+
"durationMs": 6,
|
|
1380
1380
|
"passed": true,
|
|
1381
1381
|
"score": 1,
|
|
1382
1382
|
"summary": "retrieved expected evidence",
|
|
@@ -1388,7 +1388,7 @@
|
|
|
1388
1388
|
},
|
|
1389
1389
|
{
|
|
1390
1390
|
"system": "Recent Window",
|
|
1391
|
-
"durationMs":
|
|
1391
|
+
"durationMs": 1,
|
|
1392
1392
|
"passed": true,
|
|
1393
1393
|
"score": 1,
|
|
1394
1394
|
"summary": "retrieved expected evidence",
|
|
@@ -1411,7 +1411,7 @@
|
|
|
1411
1411
|
"results": [
|
|
1412
1412
|
{
|
|
1413
1413
|
"system": "Audrey",
|
|
1414
|
-
"durationMs":
|
|
1414
|
+
"durationMs": 555,
|
|
1415
1415
|
"passed": true,
|
|
1416
1416
|
"score": 1,
|
|
1417
1417
|
"summary": "retrieved expected evidence",
|
|
@@ -1434,7 +1434,7 @@
|
|
|
1434
1434
|
},
|
|
1435
1435
|
{
|
|
1436
1436
|
"system": "Keyword + Recency",
|
|
1437
|
-
"durationMs":
|
|
1437
|
+
"durationMs": 0,
|
|
1438
1438
|
"passed": false,
|
|
1439
1439
|
"score": 0.5,
|
|
1440
1440
|
"summary": "retrieved expected evidence, but conflicting evidence still appeared later",
|
|
@@ -1469,7 +1469,7 @@
|
|
|
1469
1469
|
"results": [
|
|
1470
1470
|
{
|
|
1471
1471
|
"system": "Audrey",
|
|
1472
|
-
"durationMs":
|
|
1472
|
+
"durationMs": 418,
|
|
1473
1473
|
"passed": true,
|
|
1474
1474
|
"score": 1,
|
|
1475
1475
|
"summary": "retrieved expected evidence",
|
|
@@ -1532,7 +1532,7 @@
|
|
|
1532
1532
|
"results": [
|
|
1533
1533
|
{
|
|
1534
1534
|
"system": "Audrey",
|
|
1535
|
-
"durationMs":
|
|
1535
|
+
"durationMs": 358,
|
|
1536
1536
|
"passed": true,
|
|
1537
1537
|
"score": 1,
|
|
1538
1538
|
"summary": "retrieved expected evidence",
|
|
@@ -1593,7 +1593,7 @@
|
|
|
1593
1593
|
"results": [
|
|
1594
1594
|
{
|
|
1595
1595
|
"system": "Audrey",
|
|
1596
|
-
"durationMs":
|
|
1596
|
+
"durationMs": 289,
|
|
1597
1597
|
"passed": true,
|
|
1598
1598
|
"score": 1,
|
|
1599
1599
|
"summary": "correct abstention",
|
|
@@ -1649,7 +1649,7 @@
|
|
|
1649
1649
|
"results": [
|
|
1650
1650
|
{
|
|
1651
1651
|
"system": "Audrey",
|
|
1652
|
-
"durationMs":
|
|
1652
|
+
"durationMs": 149,
|
|
1653
1653
|
"passed": true,
|
|
1654
1654
|
"score": 1,
|
|
1655
1655
|
"summary": "retrieved expected evidence",
|
|
@@ -1660,7 +1660,7 @@
|
|
|
1660
1660
|
},
|
|
1661
1661
|
{
|
|
1662
1662
|
"system": "Vector Only",
|
|
1663
|
-
"durationMs":
|
|
1663
|
+
"durationMs": 0,
|
|
1664
1664
|
"passed": false,
|
|
1665
1665
|
"score": 0.5,
|
|
1666
1666
|
"summary": "retrieved expected evidence, but conflicting evidence still appeared later",
|
|
@@ -1672,7 +1672,7 @@
|
|
|
1672
1672
|
},
|
|
1673
1673
|
{
|
|
1674
1674
|
"system": "Keyword + Recency",
|
|
1675
|
-
"durationMs":
|
|
1675
|
+
"durationMs": 1,
|
|
1676
1676
|
"passed": false,
|
|
1677
1677
|
"score": 0,
|
|
1678
1678
|
"summary": "blocked content outranked the correct answer",
|
|
@@ -1707,7 +1707,7 @@
|
|
|
1707
1707
|
"results": [
|
|
1708
1708
|
{
|
|
1709
1709
|
"system": "Audrey",
|
|
1710
|
-
"durationMs":
|
|
1710
|
+
"durationMs": 32,
|
|
1711
1711
|
"passed": true,
|
|
1712
1712
|
"score": 1,
|
|
1713
1713
|
"summary": "retrieved expected evidence",
|
|
@@ -1731,7 +1731,7 @@
|
|
|
1731
1731
|
},
|
|
1732
1732
|
{
|
|
1733
1733
|
"system": "Keyword + Recency",
|
|
1734
|
-
"durationMs":
|
|
1734
|
+
"durationMs": 1,
|
|
1735
1735
|
"passed": false,
|
|
1736
1736
|
"score": 0,
|
|
1737
1737
|
"summary": "missed target evidence",
|
|
@@ -1768,7 +1768,7 @@
|
|
|
1768
1768
|
"results": [
|
|
1769
1769
|
{
|
|
1770
1770
|
"system": "Audrey",
|
|
1771
|
-
"durationMs":
|
|
1771
|
+
"durationMs": 211,
|
|
1772
1772
|
"passed": true,
|
|
1773
1773
|
"score": 1,
|
|
1774
1774
|
"summary": "correct abstention",
|
|
@@ -1824,7 +1824,7 @@
|
|
|
1824
1824
|
"results": [
|
|
1825
1825
|
{
|
|
1826
1826
|
"system": "Audrey",
|
|
1827
|
-
"durationMs":
|
|
1827
|
+
"durationMs": 19,
|
|
1828
1828
|
"passed": true,
|
|
1829
1829
|
"score": 1,
|
|
1830
1830
|
"summary": "retrieved expected evidence",
|
|
@@ -1847,7 +1847,7 @@
|
|
|
1847
1847
|
},
|
|
1848
1848
|
{
|
|
1849
1849
|
"system": "Keyword + Recency",
|
|
1850
|
-
"durationMs":
|
|
1850
|
+
"durationMs": 1,
|
|
1851
1851
|
"passed": false,
|
|
1852
1852
|
"score": 0.5,
|
|
1853
1853
|
"summary": "retrieved expected evidence, but conflicting evidence still appeared later",
|
|
@@ -1882,7 +1882,7 @@
|
|
|
1882
1882
|
"results": [
|
|
1883
1883
|
{
|
|
1884
1884
|
"system": "Audrey",
|
|
1885
|
-
"durationMs":
|
|
1885
|
+
"durationMs": 148,
|
|
1886
1886
|
"passed": true,
|
|
1887
1887
|
"score": 1,
|
|
1888
1888
|
"summary": "correct abstention",
|
|
@@ -1935,7 +1935,7 @@
|
|
|
1935
1935
|
"results": [
|
|
1936
1936
|
{
|
|
1937
1937
|
"system": "Audrey",
|
|
1938
|
-
"durationMs":
|
|
1938
|
+
"durationMs": 110,
|
|
1939
1939
|
"passed": true,
|
|
1940
1940
|
"score": 1,
|
|
1941
1941
|
"summary": "retrieved expected evidence",
|
|
@@ -1946,7 +1946,7 @@
|
|
|
1946
1946
|
},
|
|
1947
1947
|
{
|
|
1948
1948
|
"system": "Vector Only",
|
|
1949
|
-
"durationMs":
|
|
1949
|
+
"durationMs": 1,
|
|
1950
1950
|
"passed": false,
|
|
1951
1951
|
"score": 0,
|
|
1952
1952
|
"summary": "missed target evidence",
|
|
@@ -1996,7 +1996,7 @@
|
|
|
1996
1996
|
"results": [
|
|
1997
1997
|
{
|
|
1998
1998
|
"system": "Audrey",
|
|
1999
|
-
"durationMs":
|
|
1999
|
+
"durationMs": 24,
|
|
2000
2000
|
"passed": true,
|
|
2001
2001
|
"score": 1,
|
|
2002
2002
|
"summary": "retrieved expected evidence",
|
|
@@ -2007,7 +2007,7 @@
|
|
|
2007
2007
|
},
|
|
2008
2008
|
{
|
|
2009
2009
|
"system": "Vector Only",
|
|
2010
|
-
"durationMs":
|
|
2010
|
+
"durationMs": 0,
|
|
2011
2011
|
"passed": false,
|
|
2012
2012
|
"score": 0,
|
|
2013
2013
|
"summary": "missed target evidence",
|
|
@@ -2058,7 +2058,7 @@
|
|
|
2058
2058
|
"results": [
|
|
2059
2059
|
{
|
|
2060
2060
|
"system": "Audrey",
|
|
2061
|
-
"durationMs":
|
|
2061
|
+
"durationMs": 361,
|
|
2062
2062
|
"passed": true,
|
|
2063
2063
|
"score": 1,
|
|
2064
2064
|
"summary": "matched all required signals",
|
|
@@ -2116,7 +2116,7 @@
|
|
|
2116
2116
|
"results": [
|
|
2117
2117
|
{
|
|
2118
2118
|
"system": "Audrey",
|
|
2119
|
-
"durationMs":
|
|
2119
|
+
"durationMs": 19,
|
|
2120
2120
|
"passed": true,
|
|
2121
2121
|
"score": 1,
|
|
2122
2122
|
"summary": "matched all required signals",
|
|
@@ -2174,12 +2174,12 @@
|
|
|
2174
2174
|
"results": [
|
|
2175
2175
|
{
|
|
2176
2176
|
"system": "Audrey",
|
|
2177
|
-
"durationMs":
|
|
2177
|
+
"durationMs": 18,
|
|
2178
2178
|
"passed": true,
|
|
2179
2179
|
"score": 1,
|
|
2180
2180
|
"summary": "matched all required signals",
|
|
2181
2181
|
"topResults": [
|
|
2182
|
-
"guard_hardened:replay_rejected error:guard receipt already has an outcome:
|
|
2182
|
+
"guard_hardened:replay_rejected error:guard receipt already has an outcome: 01KX69WW0CVDB2V94KQA9KSW24",
|
|
2183
2183
|
"decision:caution verdict:caution risk:0.55 Caution: 1 memory signal, 1 medium severity found before acting.",
|
|
2184
2184
|
"warning:recent_failure severity:medium npm test failed 1x recently: Vitest failed with spawn EPERM Before re-running npm test, check what changed since the last failure."
|
|
2185
2185
|
],
|
|
@@ -2232,12 +2232,12 @@
|
|
|
2232
2232
|
"results": [
|
|
2233
2233
|
{
|
|
2234
2234
|
"system": "Audrey",
|
|
2235
|
-
"durationMs":
|
|
2235
|
+
"durationMs": 13,
|
|
2236
2236
|
"passed": true,
|
|
2237
2237
|
"score": 1,
|
|
2238
2238
|
"summary": "matched all required signals",
|
|
2239
2239
|
"topResults": [
|
|
2240
|
-
"guard_hardened:non_guard_receipt_rejected error:not a guard receipt:
|
|
2240
|
+
"guard_hardened:non_guard_receipt_rejected error:not a guard receipt: 01KX69WW0TRRANA9TAAT45W6FE",
|
|
2241
2241
|
"decision:go verdict:clear risk:0 No relevant memory risks, prior failures, or must-follow procedures were found."
|
|
2242
2242
|
],
|
|
2243
2243
|
"retrievalSummary": "guard_hardened:non_guard_receipt_rejected error:not a guard receipt: 01K | decision:go verdict:clear risk:0 No relevant memory risks, prior failure"
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import type { AudreyConfig, EmbeddingConfig, LLMConfig } from '../src/types.js';
|
|
2
|
-
export declare const VERSION = "1.1.
|
|
2
|
+
export declare const VERSION = "1.1.1";
|
|
3
3
|
export declare const SERVER_NAME = "audrey-memory";
|
|
4
4
|
export declare const DEFAULT_AGENT = "local-agent";
|
|
5
5
|
export declare const DEFAULT_DATA_DIR: string;
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
import { homedir } from 'node:os';
|
|
2
2
|
import { join } from 'node:path';
|
|
3
3
|
import { fileURLToPath } from 'node:url';
|
|
4
|
-
export const VERSION = '1.1.
|
|
4
|
+
export const VERSION = '1.1.1';
|
|
5
5
|
export const SERVER_NAME = 'audrey-memory';
|
|
6
6
|
export const DEFAULT_AGENT = 'local-agent';
|
|
7
7
|
export const DEFAULT_DATA_DIR = join(homedir(), '.audrey', 'data');
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../mcp-server/index.ts"],"names":[],"mappings":";AAeA,OAAO,EACL,MAAM,EAKP,MAAM,iBAAiB,CAAC;AAGzB,OAAO,KAAK,EAEV,gBAAgB,EAChB,kBAAkB,EAClB,aAAa,EACd,MAAM,iBAAiB,CAAC;AACzB,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,yCAAyC,CAAC;AAezE,OAAO,EAML,KAAK,SAAS,EACd,KAAK,mBAAmB,EACzB,MAAM,YAAY,CAAC;AAsBpB,OAAO,EACL,eAAe,EACf,yBAAyB,EACzB,2BAA2B,EAC3B,mBAAmB,EACnB,iBAAiB,EACjB,uBAAuB,EACvB,qBAAqB,GACtB,MAAM,sBAAsB,CAAC;AAC9B,cAAc,mBAAmB,CAAC;AAElC,eAAO,MAAM,gBAAgB,QAIlB,CAAC;
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../mcp-server/index.ts"],"names":[],"mappings":";AAeA,OAAO,EACL,MAAM,EAKP,MAAM,iBAAiB,CAAC;AAGzB,OAAO,KAAK,EAEV,gBAAgB,EAChB,kBAAkB,EAClB,aAAa,EACd,MAAM,iBAAiB,CAAC;AACzB,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,yCAAyC,CAAC;AAezE,OAAO,EAML,KAAK,SAAS,EACd,KAAK,mBAAmB,EACzB,MAAM,YAAY,CAAC;AAsBpB,OAAO,EACL,eAAe,EACf,yBAAyB,EACzB,2BAA2B,EAC3B,mBAAmB,EACnB,iBAAiB,EACjB,uBAAuB,EACvB,qBAAqB,GACtB,MAAM,sBAAsB,CAAC;AAC9B,cAAc,mBAAmB,CAAC;AAElC,eAAO,MAAM,gBAAgB,QAIlB,CAAC;AAWZ,MAAM,WAAW,YAAY;IAC3B,WAAW,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,OAAO,CAAC;IACpB,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,EAAE,OAAO,CAAC;IAChB,gBAAgB,EAAE,MAAM,GAAG,IAAI,CAAC;IAChC,KAAK,EAAE,gBAAgB,GAAG,IAAI,CAAC;IAC/B,MAAM,EAAE,kBAAkB,GAAG,IAAI,CAAC;IAClC,iBAAiB,EAAE,MAAM,GAAG,IAAI,CAAC;IACjC,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;CACtB;AAED,MAAM,MAAM,cAAc,GAAG,MAAM,GAAG,SAAS,GAAG,OAAO,CAAC;AAE1D,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,MAAM,CAAC;IACb,EAAE,EAAE,OAAO,CAAC;IACZ,QAAQ,EAAE,cAAc,CAAC;IACzB,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,MAAM,CAAC;CACf;AAED,MAAM,WAAW,YAAY;IAC3B,WAAW,EAAE,MAAM,CAAC;IACpB,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,EAAE,MAAM,CAAC;IACjB,UAAU,EAAE,MAAM,CAAC;IACnB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,GAAG,EAAE,MAAM,CAAC;IACZ,MAAM,EAAE,YAAY,CAAC;IACrB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,EAAE,EAAE,OAAO,CAAC;CACb;AA2YD,wBAAgB,kBAAkB,CAChC,IAAI,EAAE,MAAM,EACZ,GAAG,GAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAe,EACrD,MAAM,UAAQ,EACd,YAAY,UAAO,EACnB,KAAK,GAAE,SAAkB,GACxB,MAAM,CAkDR;AAibD,wBAAgB,aAAa,CAAC,OAAO,EAAE,aAAa,GAAG;IACrD,OAAO,EAAE,KAAK,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC;IACtC,eAAe,EAAE,OAAO,CAAC;IACzB,MAAM,EAAE,aAAa,CAAC,QAAQ,CAAC,CAAC;CACjC,CAMA;AAMD,wBAAgB,0BAA0B,CAAC,UAAU,SAAiB,GAAG,MAAM,CAE9E;AAED,wBAAgB,2BAA2B,CACzC,gBAAgB,EAAE,OAAO,EACzB,iBAAiB,GAAE,OAAkD,GACpE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAEzB;AA2CD,MAAM,MAAM,eAAe,GAAG,mBAAmB,CAAC;AAElD,wBAAgB,yBAAyB,CAAC,OAAO,EAAE;IACjD,YAAY,EAAE,MAAM,CAAC;IACrB,MAAM,CAAC,EAAE,OAAO,CAAC;IACjB,GAAG,CAAC,EAAE,IAAI,CAAC;CACZ,GAAG,eAAe,CAElB;AAqID,wBAAsB,cAAc,CAAC,EACnC,GAAiB,EACjB,IAAsC,GACvC,GAAE;IACD,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,EAAE,OAAO,EAAE,KAAK,IAAI,CAAC;IACnC,IAAI,CAAC,EAAE,OAAO,CAAC;CACX,GAAG,OAAO,CAAC,IAAI,CAAC,CA8IrB;AAMD,wBAAgB,iBAAiB,CAAC,EAChC,OAAqC,EACrC,cAAgD,GACjD,GAAE;IAAE,OAAO,CAAC,EAAE,MAAM,CAAC;IAAC,cAAc,CAAC,EAAE,MAAM,CAAA;CAAO,GAAG,YAAY,CAwDnE;AAED,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,YAAY,GAAG,MAAM,CAuC/D;AAED,wBAAgB,gBAAgB,CAAC,EAC/B,IAAmB,EACnB,OAAqC,EACrC,cAAgD,EAChD,GAAiB,GAClB,GAAE;IACD,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,EAAE,OAAO,EAAE,KAAK,IAAI,CAAC;CAC/B,GAAG;IAAE,MAAM,EAAE,YAAY,CAAC;IAAC,QAAQ,EAAE,MAAM,CAAA;CAAE,CAkBlD;AA0BD,wBAAgB,iBAAiB,CAAC,EAChC,OAAqC,EACrC,cAAgD,EAChD,GAAiB,EACjB,WAAmC,GACpC,GAAE;IACD,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,CAAC;IACzC,WAAW,CAAC,EAAE,MAAM,CAAC;CACjB,GAAG,YAAY,CA2JpB;AAED,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,YAAY,GAAG,MAAM,CA4B/D;AAED,wBAAgB,gBAAgB,CAAC,EAC/B,IAAmB,EACnB,OAAqC,EACrC,cAAgD,EAChD,GAAiB,EACjB,GAAiB,GAClB,GAAE;IACD,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,CAAC;IACzC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,EAAE,OAAO,EAAE,KAAK,IAAI,CAAC;CAC/B,GAAG;IAAE,MAAM,EAAE,YAAY,CAAC;IAAC,QAAQ,EAAE,MAAM,CAAA;CAAE,CAIlD;AAoED,wBAAgB,wBAAwB,CACtC,UAAU,EAAE,MAAM,CAAC,OAAO,EAC1B,MAAM,EAAE,MAAM,EACd,MAAM,GAAE,CAAC,GAAG,IAAI,EAAE,OAAO,EAAE,KAAK,IAAoB,GACnD,CAAC,OAAO,CAAC,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,KAAK,OAAO,CAAC,IAAI,CAAC,CAoDxD;AAED,wBAAgB,iBAAiB,CAAC,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,MAAM,GAAG,IAAI,CAqCzE;AAED,wBAAgB,qBAAqB,CAAC,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,MAAM,GAAG,IAAI,CA+D7E;AAED,wBAAgB,mBAAmB,CAAC,MAAM,EAAE,SAAS,GAAG,IAAI,CA+D3D"}
|